TY  - JOUR
AU  - Arya, Suraj
AU  - Deepak
AU  - Ujjawal, Krishna Kumar
PY  - 2026
DA  - 2026/04/09
TI  - An Intelligent Approach for Machine Downtime Prediction Using Ensembled Machine Learning Models
JO  - ICCK Transactions on Machine Intelligence
T2  - ICCK Transactions on Machine Intelligence
JF  - ICCK Transactions on Machine Intelligence
VL  - 2
IS  - 3
SP  - 161
EP  - 171
DO  - 10.62762/TMI.2025.597909
UR  - https://www.icck.org/article/abs/TMI.2025.597909
KW  - machine downtime
KW  - machine learning
KW  - ensembled model
KW  - machine downtime predictor
AB  - In industrial settings, unplanned machine downtime is a serious risk to profitability, operational effectiveness, and production. In order to predict machine breakdowns before they occur, this research offers a machine learning-based predictive maintenance framework that enables early prediction of machine downtime. The research is carried out using recorded data sets of industrial machines that operate according to various factors or reasons for downtime. Based on these values, prediction of downtime is possible. To guarantee data quality and consistency, several preprocessing techniques, such as imputation and normalization, were used on a dataset of 2,500 records and 16 features, ranging from hydraulic pressure and temperature to spindle vibration and torque. A variety of machine learning models, such as Random Forest, Support Vector Machines (SVM), LightGBM, XGBoost, and Gradient Boosting, were created and assessed. Although models such as SVM performed at a relatively moderate level, LightGBM and Gradient Boosting performed better than others in terms of prediction performance, with test accuracies surpassing 97%. The efficiency of machine learning in shifting from reactive to proactive maintenance is demonstrated by this work. Real-time data integration, the use of deep learning techniques, and cloud or edge platform deployment for wider industrial applicability are some future approaches to the early prediction of machine downtime.
SN  - 3068-7403
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Arya2026An,
  author = {Suraj Arya and Deepak and Krishna Kumar Ujjawal},
  title = {An Intelligent Approach for Machine Downtime Prediction Using Ensembled Machine Learning Models},
  journal = {ICCK Transactions on Machine Intelligence},
  year = {2026},
  volume = {2},
  number = {3},
  pages = {161-171},
  doi = {10.62762/TMI.2025.597909},
  url = {https://www.icck.org/article/abs/TMI.2025.597909},
  abstract = {In industrial settings, unplanned machine downtime is a serious risk to profitability, operational effectiveness, and production. In order to predict machine breakdowns before they occur, this research offers a machine learning-based predictive maintenance framework that enables early prediction of machine downtime. The research is carried out using recorded data sets of industrial machines that operate according to various factors or reasons for downtime. Based on these values, prediction of downtime is possible. To guarantee data quality and consistency, several preprocessing techniques, such as imputation and normalization, were used on a dataset of 2,500 records and 16 features, ranging from hydraulic pressure and temperature to spindle vibration and torque. A variety of machine learning models, such as Random Forest, Support Vector Machines (SVM), LightGBM, XGBoost, and Gradient Boosting, were created and assessed. Although models such as SVM performed at a relatively moderate level, LightGBM and Gradient Boosting performed better than others in terms of prediction performance, with test accuracies surpassing 97\%. The efficiency of machine learning in shifting from reactive to proactive maintenance is demonstrated by this work. Real-time data integration, the use of deep learning techniques, and cloud or edge platform deployment for wider industrial applicability are some future approaches to the early prediction of machine downtime.},
  keywords = {machine downtime, machine learning, ensembled model, machine downtime predictor},
  issn = {3068-7403},
  publisher = {Institute of Central Computation and Knowledge}
}